Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4055 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1625200 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1594405 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1288467 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1603741 (Python Code)

Max Activating Token Index: 786

Text #4

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1465033 (Python Code)

Max Activating Token Index: 284

Text #5

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1567456 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1557406 (Python Code)

Max Activating Token Index: 475

Text #7

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1177738 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1553012 (Python Code)

Max Activating Token Index: 718

Text #9

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1448789 (Python Code)

Max Activating Token Index: 711

Text #10

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0336. Min Act: -0.0001

Data Index: 669959 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0333. Min Act: -0.0001

Data Index: 580764 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1561474 (Python Code)

Max Activating Token Index: 492

Text #13

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0327. Min Act: -0.0001

Data Index: 794025 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1575304 (Python Code)

Max Activating Token Index: 124

Text #15

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0325. Min Act: -0.0001

Data Index: 671540 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1499939 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1538226 (Python Code)

Max Activating Token Index: 508

Text #18

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0314. Min Act: -0.0001

Data Index: 17298 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0313. Min Act: -0.0001

Data Index: 135774 (C4 (Web Text))

Max Activating Token Index: 619